运行ann_to_snn.py文件后，报错ValueError: ('cannot find tensor Size', torch.Size([1, 32, 416, 416]))

[Wang-jun-yu]

相同的parser在train.py文件夹下可以正常运行，但在ann_to_snn.py下报错。 我的数据集图像大小为800*800，修改下列parser为： parser.add_argument('--img-size', nargs='+', type=int, default=[800, 800], help='[min_train, max-train, test]') 会报错ValueError: ('cannot find tensor Size', torch.Size([1, 32, 416, 416]))，如果改为了default=[416, 416]，依然报错：ValueError: ('cannot find tensor Size', torch.Size([1, 32, 416, 416])) 请问如何修改才能不报错？

以下为具体报错信息：

C:\Users\Lenovo.conda\envs\venv\yolov3-envs\python.exe E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\ann_to_snn.py Namespace(augment=False, batch_size=1, cache_images=False, cfg='cfg/yolov3.cfg', channel_wise=False, conf_thres=0.001, data='data/myvoc.data', device='0', img_size=[416, 416, 416], iou_thres=0.5, multi_scale=False, rect=False, reset_mode='subtraction', save_file='yolov3-my-snn', save_json=False, single_cls=False, statistics_iters=30, task='test', timesteps=100, weights='weights/best.pt') Using CUDA device0 _CudaDeviceProperties(name='NVIDIA GeForce RTX 3060 Laptop GPU', total_memory=6143MB)

Caching labels E:\DataSate\labels\train.npy (5043 found, 0 missing, 0 empty, 0 duplicate, for 5043 images): 100%|██████████| 5043/5043 [00:00<00:00, 19846.45it/s] Model Summary: 222 layers, 6.15237e+07 parameters, 6.15237e+07 gradients add node conv1: ['dag_input0']->['conv1_out1'] Traceback (most recent call last): File "E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\ann_to_snn.py", line 182, in transformer.inference_get_status(dataloader, opt.statistics_iters) File "E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\spiking_utils\snn_transformer.py", line 94, in inference_get_status self.init_dag([data]) File "E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\spiking_utils\snn_transformer.py", line 69, in init_dag self.snn_dag = ann_parser.parse_ann_model(self.original_net, inputs) File "E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\spiking_utils\ann_parser.py", line 221, in parse_ann_model model(warpped_input) File "C:\Users\Lenovo.conda\envs\venv\yolov3-envs\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl result = self.forward(input, kwargs) File "E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\ann_to_snn.py", line 65, in forward x = self.listi File "C:\Users\Lenovo.conda\envs\venv\yolov3-envs\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl result = self.forward(*input, *kwargs) File "C:\Users\Lenovo.conda\envs\venv\yolov3-envs\lib\site-packages\torch\nn\modules\container.py", line 117, in forward input = module(input) File "C:\Users\Lenovo.conda\envs\venv\yolov3-envs\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl result = self.forward(input, kwargs) File "C:\Users\Lenovo.conda\envs\venv\yolov3-envs\lib\site-packages\torch\nn\modules\conv.py", line 423, in forward return self._conv_forward(input, self.weight) File "C:\Users\Lenovo.conda\envs\venv\yolov3-envs\lib\site-packages\torch\nn\modules\conv.py", line 420, in _conv_forward self.padding, self.dilation, self.groups) File "E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\spiking_utils\ann_parser.py", line 69, in conv2d_wrapper in_nodes = [find_node_by_tensor(inp)] File "E:\SNN\PyTorch-Spiking-YOLOv3-ultralytics\spiking_utils\ann_parser.py", line 10, in find_node_by_tensor raise ValueError("cannot find tensor Size", tensor.size()) ValueError: ('cannot find tensor Size', torch.Size([1, 32, 416, 416]))

Process finished with exit code 1

[sun133233]

同样遇到这个问题，请问你解决了吗

[jsckdon]

@sun133233 请问您解决了吗

[Shenyiyu1]

@sun133233 请问您解决了吗

请问你们跑通这个代码了码，为啥我用gpu训练的时候，老显示2个设备报错 RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!